Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 245 670   6 184 174 981 132 894 751 348 740 948 661  48  49  90 596 949 570 800
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 174 348 132  48  NA 948  49 245 740  NA  90 596 894 800 184  NA 661 751   6 981 949 570 670
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 2 1 3 5 1 3 3 5 4 3
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "t" "n" "f" "y" "j" "K" "Y" "Z" "P" "A"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  6 12 18
which( manyNumbersWithNA > 900 )
[1]  6 20 21
which( is.na( manyNumbersWithNA ) )
[1]  5 10 16

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 981 948 949
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 981 948 949
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 981 948 949

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "K" "Y" "Z" "P" "A"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "t" "n" "f" "y" "j"
manyNumbers %in% 300:600
 [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE
[19]  TRUE FALSE
which( manyNumbers %in% 300:600 )
[1] 10 17 19
sum( manyNumbers %in% 300:600 )
[1] 3

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "small" "small" "small" NA      "large" "small" "small" "large" NA      "small" "large" "large" "large"
[15] "small" NA      "large" "large" "small" "large" "large" "large" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "small"   "small"   "small"   "UNKNOWN" "large"   "small"   "small"   "large"   "UNKNOWN" "small"  
[12] "large"   "large"   "large"   "small"   "UNKNOWN" "large"   "large"   "small"   "large"   "large"   "large"  
[23] "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0   0   0   0  NA 948   0   0 740  NA   0 596 894 800   0  NA 661 751   0 981 949 570 670

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 2 1 3 5 4
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  2  1  3  5  4
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE FALSE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 20
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 981
which.min( manyNumbersWithNA )
[1] 19
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 6
range( manyNumbersWithNA, na.rm = TRUE )
[1]   6 981

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 174 348 132  48  NA 948  49 245 740  NA  90 596 894 800 184  NA 661 751   6 981 949 570 670
sort( manyNumbersWithNA )
 [1]   6  48  49  90 132 174 184 245 348 570 596 661 670 740 751 800 894 948 949 981
sort( manyNumbersWithNA, na.last = TRUE )
 [1]   6  48  49  90 132 174 184 245 348 570 596 661 670 740 751 800 894 948 949 981  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 981 949 948 894 800 751 740 670 661 596 570 348 245 184 174 132  90  49  48   6  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 174 348 132  48  NA
order( manyNumbersWithNA[1:5] )
[1] 4 3 1 2 5
rank( manyNumbersWithNA[1:5] )
[1] 3 4 2 1 5
sort( mixedLetters )
 [1] "A" "f" "j" "K" "n" "P" "t" "y" "Y" "Z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 5 9 9 9 5 2 5 5 1 5
rank( manyDuplicates, ties.method = "min" )
 [1] 3 8 8 8 3 2 3 3 1 3
rank( manyDuplicates, ties.method = "random" )
 [1]  7  8  9 10  6  2  5  4  1  3

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000  0.15021807  0.27517033  0.83855149 -0.15026076
[10]  0.93050383 -0.08539683  0.24923108 -0.53823340  0.01422160  0.26408372
round( v, 0 )
 [1] -1  0  0  0  1  0  0  1  0  1  0  0 -1  0  0
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  0.2  0.3  0.8 -0.2  0.9 -0.1  0.2 -0.5  0.0  0.3
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  0.15  0.28  0.84 -0.15  0.93 -0.09  0.25 -0.54  0.01  0.26
floor( v )
 [1] -1 -1  0  0  1  0  0  0 -1  0 -1  0 -1  0  0
ceiling( v )
 [1] -1  0  0  1  1  1  1  1  0  1  0  1  0  1  1

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2022 Biomedical Data Sciences (BDS) | LUMC